AI Engineer
First seen by Alion on Sep 19, 2026.
AI Engineer - LLM & AI Systems
Location : Bangalore
Employment Type : Full-time
Experience : 3+ Years
About the Role :
We are looking for an AI Engineer to design, build, and deploy AI-powered features that sit at the core of a next-generation technology platform.
The role involves building reliable LLM systems, evaluation infrastructure, RAG pipelines, and agentic workflows that can translate complex real-world workflows into accurate, scalable, and production-ready AI experiences.
You will work closely with product, engineering, and domain experts, taking significant ownership from experimentation and prototyping through production deployment.
Key Responsibilities :
- Build and maintain model evaluation and testing harnesses, including benchmark runners, regression suites, prompt test beds, and model comparison frameworks.
- Design, develop, and ship LLM-powered production features from prototype to deployment.
- Build and optimize RAG pipelines, agentic workflows, tool-use systems, and orchestration layers.
- Develop effective prompting and context strategies to improve accuracy, consistency, and cost efficiency.
- Integrate and evaluate proprietary and open-source foundation models based on quality, latency, reliability, and cost.
- Develop evaluation frameworks and quality checks to systematically measure and improve AI performance.
- Implement guardrails, fallback mechanisms, monitoring, and observability for production AI systems.
- Collaborate with product, engineering, and domain teams to convert complex workflows into practical AI solutions.
- Continuously improve AI systems based on evaluation results and real-world usage data.
Requirements :
- 3+ years of hands-on experience building and deploying applications or systems using LLMs and AI models.
- Experience building AI evaluation infrastructure, model harnesses, benchmark runners, test suites, or similar systems.
- Strong practical experience with RAG, agentic AI, tool use, prompt engineering, and AI orchestration.
- Strong backend and software engineering fundamentals with experience building reliable production systems.
- Experience designing AI evaluations, quality checks, and regression testing frameworks.
- Good understanding of the LLM ecosystem, including API-based and open-source models.
- Understanding of prompting vs. fine-tuning and model selection trade-offs.
- Ability to work independently, take ownership, and operate effectively in a fast-paced environment.
Preferred :
- Experience with legal technology, document intelligence, or document-heavy workflows.
- Experience working on high-stakes or regulated AI applications.
- Familiarity with production AI observability, monitoring, and reliability practices.
- Experience working with multiple LLM providers or model architectures.
What the Role Offers :
- Opportunity to build AI infrastructure and intelligent product features from the ground up.
- Significant ownership and direct exposure to product and business decisions.
- Opportunity to work closely with experienced AI engineers, product teams, and domain experts.
- Competitive compensation based on experience and expertise.
- High-impact role in a rapidly evolving AI-focused environment.
Skills
Artificial Intelligence, LLM, RAG, Agentic AI, Prompt Engineering, AI Infrastructure